Daofeng Li

Yiyou Sun, Xinyang Han, Weichen Zhang et al.

Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional domains. We argue that this gap is largely an evaluation problem: widely used benchmarks lack sustained performance measurement on real and economically valuable workflows. This paper introduces Agents' Last Exam (ALE), a benchmark designed to evaluate AI agents on long-horizon, economically valuable, real-world tasks with verifiable outcomes. Developed in collaboration with 250+ industry experts, ALE covers non-physical industries defined with reference to O*NET / SOC 2018 (the U.S. federal occupational taxonomy). It is organized around a task taxonomy with 55 subfields grouped into 13 industry clusters covering 1K+ tasks. Current results show that the hardest tier remains far from saturated: across mainstream harness and backbone configurations, the average full pass rate is 2.6%. ALE is designed as a living benchmark: its task pool grows continuously as new workflows and industries are onboarded. More broadly, ALE is intended not merely as another leaderboard, but as an instrument for closing the gap between benchmark success and GDP-relevant impact.

Long Phan, Alice Gatti, Ziwen Han et al. · amazon-science, apple-ml

Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achieve over 90\% accuracy on popular benchmarks like MMLU, limiting informed measurement of state-of-the-art LLM capabilities. In response, we introduce Humanity's Last Exam (HLE), a multi-modal benchmark at the frontier of human knowledge, designed to be the final closed-ended academic benchmark of its kind with broad subject coverage. HLE consists of 2,500 questions across dozens of subjects, including mathematics, humanities, and the natural sciences. HLE is developed globally by subject-matter experts and consists of multiple-choice and short-answer questions suitable for automated grading. Each question has a known solution that is unambiguous and easily verifiable, but cannot be quickly answered via internet retrieval. State-of-the-art LLMs demonstrate low accuracy and calibration on HLE, highlighting a significant gap between current LLM capabilities and the expert human frontier on closed-ended academic questions. To inform research and policymaking upon a clear understanding of model capabilities, we publicly release HLE at https://lastexam.ai.

Zhikun Chen, Daofeng Li, Jinkang Zhu et al.

Federated learning (FL) is a burgeoning distributed machine learning framework where a central parameter server (PS) coordinates many local users to train a globally consistent model. Conventional federated learning inevitably relies on a centralized topology with a PS. As a result, it will paralyze once the PS fails. To alleviate such a single point failure, especially on the PS, some existing work has provided decentralized FL (DFL) implementations like CDSGD and D-PSGD to facilitate FL in a decentralized topology. However, there are still some problems with these methods, e.g., significant divergence between users' final models in CDSGD and a network-wide model average necessity in D-PSGD. In order to solve these deficiency, this paper devises a new DFL implementation coined as DACFL, where each user trains its model using its own training data and exchanges the intermediate models with its neighbors through a symmetric and doubly stochastic matrix. The DACFL treats the progress of each user's local training as a discrete-time process and employs a first order dynamic average consensus (FODAC) method to track the \textit{average model} in the absence of the PS. In this paper, we also provide a theoretical convergence analysis of DACFL on the premise of i.i.d data to strengthen its rationality. The experimental results on MNIST, Fashion-MNIST and CIFAR-10 validate the feasibility of our solution in both time-invariant and time-varying network topologies, and declare that DACFL outperforms D-PSGD and CDSGD in most cases.

Zhikun Chen, Daofeng Li, Ming Zhao et al.

Federated learning (FL) enables massive distributed Information and Communication Technology (ICT) devices to learn a global consensus model without any participants revealing their own data to the central server. However, the practicality, communication expense and non-independent and identical distribution (Non-IID) data challenges in FL still need to be concerned. In this work, we propose the Semi-Federated Learning (Semi-FL) which differs from the FL in two aspects, local clients clustering and in-cluster training. A sequential training manner is designed for our in-cluster training in this paper which enables the neighboring clients to share their learning models. The proposed Semi-FL can be easily applied to future mobile communication networks and require less up-link transmission bandwidth. Numerical experiments validate the feasibility, learning performance and the robustness to Non-IID data of the proposed Semi-FL. The Semi-FL extends the existing potentials of FL.